Surrogate-Based Differentiable Pipeline for Shape Optimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908651155881984 |
|---|---|
| author | Rehmann, Andrin Black, Nolan Bjorgaard, Josiah Angioi, Alessandro Paleyes, Andrei Heim, Niklas Häfner, Dion Lavin, Alexander |
| author_facet | Rehmann, Andrin Black, Nolan Bjorgaard, Josiah Angioi, Alessandro Paleyes, Andrei Heim, Niklas Häfner, Dion Lavin, Alexander |
| contents | Gradient-based optimization of engineering designs is limited by non-differentiable components in the typical computer-aided engineering (CAE) workflow, which calculates performance metrics from design parameters. While gradient-based methods could provide noticeable speed-ups in high-dimensional design spaces, codes for meshing, physical simulations, and other common components are not differentiable even if the math or physics underneath them is. We propose replacing non-differentiable pipeline components with surrogate models which are inherently differentiable. Using a toy example of aerodynamic shape optimization, we demonstrate an end-to-end differentiable pipeline where a 3D U-Net full-field surrogate replaces both meshing and simulation steps by training it on the mapping between the signed distance field (SDF) of the shape and the fields of interest. This approach enables gradient-based shape optimization without the need for differentiable solvers, which can be useful in situations where adjoint methods are unavailable and/or hard to implement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10761 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Surrogate-Based Differentiable Pipeline for Shape Optimization Rehmann, Andrin Black, Nolan Bjorgaard, Josiah Angioi, Alessandro Paleyes, Andrei Heim, Niklas Häfner, Dion Lavin, Alexander Computational Engineering, Finance, and Science Artificial Intelligence Machine Learning Differential Geometry Gradient-based optimization of engineering designs is limited by non-differentiable components in the typical computer-aided engineering (CAE) workflow, which calculates performance metrics from design parameters. While gradient-based methods could provide noticeable speed-ups in high-dimensional design spaces, codes for meshing, physical simulations, and other common components are not differentiable even if the math or physics underneath them is. We propose replacing non-differentiable pipeline components with surrogate models which are inherently differentiable. Using a toy example of aerodynamic shape optimization, we demonstrate an end-to-end differentiable pipeline where a 3D U-Net full-field surrogate replaces both meshing and simulation steps by training it on the mapping between the signed distance field (SDF) of the shape and the fields of interest. This approach enables gradient-based shape optimization without the need for differentiable solvers, which can be useful in situations where adjoint methods are unavailable and/or hard to implement. |
| title | Surrogate-Based Differentiable Pipeline for Shape Optimization |
| topic | Computational Engineering, Finance, and Science Artificial Intelligence Machine Learning Differential Geometry |
| url | https://arxiv.org/abs/2511.10761 |